Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
16,761 documents
The discussion reviews assumptions for a custom equity backtester using bar data, especially for strategies that hold positions for days. For conservative simulated fills, one answer recommends adverse bar extremes after a signal: high prices for long…
The discussion addresses how to set an upper-domain boundary when numerically pricing options with finite differences. It recommends using linear behavior in an extreme model state as a generic boundary approximation for many products. In mathematical terms,…
The document asks how maximum drawdown varies with the mean and standard deviation of daily returns and the length of the return series. It frames the problem with simulated paths: draw daily observations from a normal distribution, calculate each path’s…
The discussion collects suggestions for obtaining intraday DAX or DAX futures data, with an emphasis on one-minute bars and affordability. It mentions exchange data for DAX futures, downloadable DAX series from a broker-data source whose instrument type may…
The discussion surveys ways to combine financial series observed at different frequencies and use them in forecasts. MIDAS models incorporate higher-frequency predictors into a lower-frequency target, such as daily market data in a quarterly economic…
The document describes a simplified way to represent an active long volatility allocation discussed in a portfolio research paper. The proposed rule monitors the equity market over a rolling three-month window and buys options in the direction of a…
This discussion asks whether input attributes need to be scaled before gradient tree boosting. One answer says scaling is generally unnecessary for tree-based boosting, since the distance-based concerns that motivate normalization for methods such as support…
This question compares an extreme value theory approach to value-at-risk with simulation from empirical return distributions. The proposed EVT workflow models the center of returns with a Gaussian kernel and the tails with a generalized Pareto distribution,…
The document outlines three limitations of Brownian motion as a model for financial prices. Its continuous paths cannot represent sudden price jumps, and its Gaussian assumptions may fail to capture the distribution of market returns. It also raises…
The document describes a CPI forecasting regression whose author sees a moving average of the residuals moving in the same direction as CPI. The author asks whether this suggests omitted-variable bias, biased coefficients, or another modeling problem. The…
The document presents competing views on calculating a strategy’s Sharpe ratio when it has no open positions. Some responses argue for excluding such days because they have no realized strategy return and including zero or forward-filled observations could…
The discussion explains why a simulated delta hedge may retain tracking error and how to account for changing positions. In the Black–Scholes framework, hedge error should shrink as rehedging intervals become smaller when the simulated underlying follows the…
The document asks why a manually calculated Sharpe ratio differs from the value shown by TradingView for a backtest with six trades. It provides a short series of eight daily profit observations, including both positive and negative values and several…
The document examines a proposed test of whether empirical price data follow an Ornstein-Uhlenbeck (OU) process. The described procedure estimates OU parameters by maximum likelihood, simulates a new path using those estimates, then fits the OU model again…
The document presents a workflow for forecasting stock volatility with a GARCH(1,1) model through R’s rugarch package called from Python with rpy2. It calculates daily log returns, fits a Student-t model to returns scaled as percentages, reserves a final…
This example explains how to impose linear restrictions on the cointegrating vectors of a Johansen vector error correction model. It begins with simulated series sharing a common stochastic trend, estimates a model with four cointegrating relationships, and…
The question asks whether two sets of bootstrapped Value at Risk estimates, generated from returns before and after a recession, can be compared with a t-test. The response says that non-normality in the underlying returns does not automatically rule out a…
The document asks why White’s Bootstrap Reality Check (BRC) evaluates the best-performing strategy in a group. It proposes applying the same procedure to the second-best strategy, then to lower-ranked strategies, by comparing each strategy’s scaled mean…
The document describes a Monte Carlo resampling approach to mean-variance portfolio optimization. It outlines fitting return distributions to assets, simulating returns while respecting assumptions about expected returns, volatility, and correlation,…
The document considers whether macroeconomic variables such as GDP growth, inflation, employment, and fiscal spending relate to company revenues or earnings across industries. It proposes using company-level panel data and asks whether a fixed-effects model…
The problem describes a European call that must be sold if an independent event occurs, at the lower of its current value and its original purchase price. One response reframes the contract as a standard call minus the value of a compound call written on…
The note explains that whether to include a shutdown period in a strategy’s Sharpe ratio depends on why the strategy stopped trading and what the statistic is intended to measure. If a discretionary trader deliberately moves to cash, that choice is part of…
The discussion examines how to estimate the six-month roll-down of a five-year interest rate swap. It challenges simply subtracting a five-year spot rate and a four-and-a-half-year spot rate, then explains how to represent the original swap after time…
The document asks how to count degrees of freedom when assessing a trading system’s complexity. It presents a framework that combines the system’s rules with the market observations those rules consume, and cites examples in which two moving averages on the…